{"total":262,"rows":[{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322,"area":null},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177,"area":null},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320,"area":null},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","cited_by_count":320,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193,"area":null},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171,"area":null},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169,"area":null},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162,"area":null},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147,"area":null},{"id":"2104.01633","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","created":"2021-04-04","cited_by_count":138,"area":null},{"id":"2108.07781","title":"End-to-End Dense Video Captioning with Parallel Decoding","created":"2021-08-17","cited_by_count":133,"area":null},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110,"area":null},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96,"area":null},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84,"area":null},{"id":"2204.01680","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","created":"2022-04-04","cited_by_count":79,"area":null},{"id":"2108.02833","title":"Elaborative Rehearsal for Zero-shot Action Recognition","created":"2021-08-05","cited_by_count":77,"area":null},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2411.10332","title":"Number it: Temporal Grounding Videos like Flipping Manga","created":"2024-11-15","cited_by_count":65,"area":null},{"id":"2107.00285","title":"iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis","created":"2021-07-01","cited_by_count":63,"area":null},{"id":"2105.11107","title":"FineAction: A Fine-Grained Video Dataset for Temporal Action Localization","created":"2021-05-24","cited_by_count":61,"area":null},{"id":"2108.01959","title":"Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning","created":"2021-08-04","cited_by_count":58,"area":null},{"id":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","cited_by_count":58,"area":null},{"id":"2107.00085","title":"CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation","created":"2021-06-30","cited_by_count":52,"area":null},{"id":"2108.08121","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","created":"2021-08-18","cited_by_count":52,"area":null},{"id":"2112.03596","title":"E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","created":"2021-12-07","cited_by_count":50,"area":null},{"id":"2210.05357","title":"Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment","created":"2022-10-11","cited_by_count":50,"area":null},{"id":"2207.07097","title":"ReAct: Temporal Action Detection with Relational Queries","created":"2022-07-14","cited_by_count":48,"area":null},{"id":"2403.05234","title":"Benchmarking Micro-action Recognition: Dataset, Methods, and Applications","created":"2024-03-08","cited_by_count":48,"area":null},{"id":"2212.04842","title":"PIVOT: Prompting for Video Continual Learning","created":"2022-12-09","cited_by_count":45,"area":null},{"id":"2308.10794","title":"MGMAE: Motion Guided Masking for Video Masked Autoencoding","created":"2023-08-21","cited_by_count":41,"area":null},{"id":"2104.11452","title":"SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos","created":"2021-04-23","cited_by_count":40,"area":null},{"id":"2210.06096","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","created":"2022-10-12","cited_by_count":39,"area":null},{"id":"2304.04617","title":"VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views","created":"2023-04-10","cited_by_count":38,"area":null},{"id":"2309.07911","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","created":"2023-09-14","cited_by_count":32,"area":null},{"id":"2112.03587","title":"TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning","created":"2021-12-07","cited_by_count":31,"area":null},{"id":"2301.01380","title":"Ego-Only: Egocentric Action Detection without Exocentric Transferring","created":"2023-01-03","cited_by_count":31,"area":null},{"id":"2305.13500","title":"Learning Emotion Representations from Verbal and Nonverbal Communication","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2107.04932","title":"Aligning Correlation Information for Domain Adaptation in Action Recognition","created":"2021-07-11","cited_by_count":30,"area":null},{"id":"2308.12962","title":"Motion-Guided Masking for Spatiotemporal Representation Learning","created":"2023-08-24","cited_by_count":30,"area":null},{"id":"2207.11660","title":"MAR: Masked Autoencoders for Efficient Action Recognition","created":"2022-07-24","cited_by_count":29,"area":null},{"id":"2301.03046","title":"STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition","created":"2023-01-08","cited_by_count":29,"area":null},{"id":"2201.09381","title":"vCLIMB: A Novel Video Class Incremental Learning Benchmark","created":"2022-01-23","cited_by_count":28,"area":null},{"id":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","cited_by_count":28,"area":null},{"id":"2203.14957","title":"Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning","created":"2022-03-28","cited_by_count":27,"area":null},{"id":"2211.12883","title":"Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground","created":"2022-11-23","cited_by_count":27,"area":null},{"id":"2211.00882","title":"DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Network","created":"2022-11-02","cited_by_count":26,"area":null},{"id":"2203.07112","title":"RCL: Recurrent Continuous Localization for Temporal Action Detection","created":"2022-03-14","cited_by_count":25,"area":null},{"id":"2202.13377","title":"Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation","created":"2022-02-27","cited_by_count":23,"area":null},{"id":"2210.16820","title":"Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition","created":"2022-10-30","cited_by_count":22,"area":null},{"id":"2311.15367","title":"BatchNorm-based Weakly Supervised Video Anomaly Detection","created":"2023-11-26","cited_by_count":22,"area":null},{"id":"2106.14118","title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization","created":"2021-06-27","cited_by_count":21,"area":null},{"id":"2109.11593","title":"Long Short View Feature Decomposition via Contrastive Video Representation Learning","created":"2021-09-23","cited_by_count":21,"area":null},{"id":"2111.12449","title":"Background-Click Supervision for Temporal Action Localization","created":"2021-11-24","cited_by_count":21,"area":null},{"id":"2301.12688","title":"Dynamic Storyboard Generation in an Engine-based Virtual Environment for Video Production","created":"2023-01-30","cited_by_count":21,"area":null},{"id":"2306.11726","title":"How can objects help action recognition?","created":"2023-06-20","cited_by_count":21,"area":null},{"id":"2201.03080","title":"The State of Aerial Surveillance: A Survey","created":"2022-01-09","cited_by_count":20,"area":null},{"id":"2402.18137","title":"DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning","created":"2024-02-28","cited_by_count":20,"area":null},{"id":"2407.05311","title":"MMAD: Multi-label Micro-Action Detection in Videos","created":"2024-07-07","cited_by_count":20,"area":null},{"id":"2107.11639","title":"Self-Conditioned Probabilistic Learning of Video Rescaling","created":"2021-07-24","cited_by_count":19,"area":null},{"id":"2204.00486","title":"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval","created":"2022-04-01","cited_by_count":19,"area":null},{"id":"2312.05719","title":"DVANet: Disentangling View and Action Features for Multi-View Action Recognition","created":"2023-12-10","cited_by_count":19,"area":null},{"id":"2106.11812","title":"Proposal Relation Network for Temporal Action Detection","created":"2021-06-20","cited_by_count":18,"area":null},{"id":"2108.04294","title":"Learning to Cut by Watching Movies","created":"2021-08-09","cited_by_count":18,"area":null},{"id":"2106.06326","title":"TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation","created":"2021-06-11","cited_by_count":17,"area":null},{"id":"2202.02813","title":"A Coding Framework and Benchmark towards Low-Bitrate Video Understanding","created":"2022-02-06","cited_by_count":17,"area":null},{"id":"2207.08625","title":"Unifying Event Detection and Captioning as Sequence Generation via Pre-Training","created":"2022-07-18","cited_by_count":17,"area":null},{"id":"2303.03856","title":"Event Voxel Set Transformer for Spatiotemporal Representation Learning on Event Streams","created":"2023-03-07","cited_by_count":17,"area":null},{"id":"2107.10771","title":"EAN: Event Adaptive Network for Enhanced Action Recognition","created":"2021-07-22","cited_by_count":16,"area":null},{"id":"2110.12358","title":"A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark","created":"2021-10-24","cited_by_count":16,"area":null},{"id":"2207.10448","title":"An Efficient Spatio-Temporal Pyramid Transformer for Action Detection","created":"2022-07-21","cited_by_count":16,"area":null},{"id":"2304.08799","title":"Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization","created":"2023-04-18","cited_by_count":16,"area":null},{"id":"2103.13567","title":"Deepfake Forensics via An Adversarial Game","created":"2021-03-25","cited_by_count":15,"area":null},{"id":"2211.10636","title":"EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens","created":"2022-11-19","cited_by_count":15,"area":null},{"id":"2301.07944","title":"Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition","created":"2023-01-19","cited_by_count":15,"area":null},{"id":"2309.02423","title":"EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding","created":"2023-09-05","cited_by_count":15,"area":null},{"id":"2309.16309","title":"Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attention","created":"2023-09-28","cited_by_count":15,"area":null},{"id":"2204.09271","title":"A Survey of Video-based Action Quality Assessment","created":"2022-04-20","cited_by_count":14,"area":null},{"id":"2307.03166","title":"VideoGLUE: Video General Understanding Evaluation of Foundation Models","created":"2023-07-06","cited_by_count":14,"area":null},{"id":"2409.06299","title":"Enhancing Long Video Understanding via Hierarchical Event-Based Memory","created":"2024-09-10","cited_by_count":14,"area":null},{"id":"2205.13313","title":"Cross-Architecture Self-supervised Video Representation Learning","created":"2022-05-26","cited_by_count":13,"area":null},{"id":"2301.00794","title":"STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos","created":"2023-01-02","cited_by_count":13,"area":null},{"id":"2309.05590","title":"Temporal Action Localization with Enhanced Instant Discriminability","created":"2023-09-11","cited_by_count":13,"area":null},{"id":"2402.02941","title":"Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey","created":"2024-02-05","cited_by_count":13,"area":null},{"id":"2404.08561","title":"IDD-X: A Multi-View Dataset for Ego-relative Important Object Localization and Explanation in Dense and Unstructured Traffic","created":"2024-04-12","cited_by_count":13,"area":null},{"id":"2201.06268","title":"Continual Transformers: Redundancy-Free Attention for Online Inference","created":"2022-01-17","cited_by_count":12,"area":null},{"id":"2207.10664","title":"Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset","created":"2022-07-21","cited_by_count":12,"area":null},{"id":"2301.03330","title":"HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition","created":"2023-01-09","cited_by_count":12,"area":null},{"id":"2306.04216","title":"MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos","created":"2023-06-07","cited_by_count":12,"area":null},{"id":"2309.01265","title":"SOAR: Scene-debiasing Open-set Action Recognition","created":"2023-09-03","cited_by_count":12,"area":null},{"id":"2311.18825","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","created":"2023-11-30","cited_by_count":12,"area":null},{"id":"2312.02914","title":"Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training","created":"2023-12-05","cited_by_count":12,"area":null},{"id":"2402.03019","title":"Taylor Videos for Action Recognition","created":"2024-02-05","cited_by_count":12,"area":null},{"id":"2404.05215","title":"Spatio-Temporal Attention and Gaussian Processes for Personalized Video Gaze Estimation","created":"2024-04-08","cited_by_count":12,"area":null},{"id":"2110.14381","title":"Temporal-attentive Covariance Pooling Networks for Video Recognition","created":"2021-10-27","cited_by_count":11,"area":null},{"id":"2112.04674","title":"DualFormer: Local-Global Stratified Transformer for Efficient Video Recognition","created":"2021-12-09","cited_by_count":11,"area":null},{"id":"2309.14809","title":"ENIGMA-51: Towards a Fine-Grained Understanding of Human-Object Interactions in Industrial Scenarios","created":"2023-09-26","cited_by_count":11,"area":null},{"id":"2311.16444","title":"Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos","created":"2023-11-28","cited_by_count":11,"area":null},{"id":"2407.14744","title":"A Comprehensive Review of Few-shot Action Recognition","created":"2024-07-20","cited_by_count":11,"area":null},{"id":"2503.17132","title":"Temporal-Guided Spiking Neural Networks for Event-Based Human Action Recognition","created":"2025-03-21","cited_by_count":11,"area":null}],"next_cursor":"100"}